{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:27:42Z","timestamp":1774895262527,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705489","type":"print"},{"value":"9783031705496","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70549-6_23","type":"book-chapter","created":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:02:15Z","timestamp":1725786135000},"page":"387-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Improving Automatic Text Recognition with\u00a0Language Models in\u00a0the\u00a0PyLaia Open-Source Library"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6174-9865","authenticated-orcid":false,"given":"Sol\u00e8ne","family":"Tarride","sequence":"first","affiliation":[]},{"given":"Yoann","family":"Schneider","sequence":"additional","affiliation":[]},{"given":"Marie","family":"Generali-Lince","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0618-7852","authenticated-orcid":false,"given":"M\u00e9lodie","family":"Boillet","sequence":"additional","affiliation":[]},{"given":"Bastien","family":"Abadie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7508-4080","authenticated-orcid":false,"given":"Christopher","family":"Kermorvant","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","unstructured":"Beyer, Y., Solberg, P.E.: NorHand v3\/Dataset for Handwritten Text Recognition in Norwegian (2023). https:\/\/doi.org\/10.5281\/zenodo.10255840","DOI":"10.5281\/zenodo.10255840"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Beyer, Y., Solberg, P.E.: Norhand v2\/Dataset for Handwritten Text Recognition in Norwegian [Data Set] (2024). https:\/\/doi.org\/10.5281\/zenodo.10555698","DOI":"10.5281\/zenodo.10555698"},{"key":"23_CR3","unstructured":"Blecher, L., Cucurull, G., Scialom, T., Stojnic, R.: Nougat: Neural Optical Understanding for Academic Documents (2023)"},{"issue":"4","key":"23_CR4","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1006\/csla.1999.0128","volume":"13","author":"SF Chen","year":"1999","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Comput. Speech Lang. 13(4), 359\u2013394 (1999). https:\/\/doi.org\/10.1006\/csla.1999.0128","journal-title":"Comput. Speech Lang."},{"key":"23_CR5","doi-asserted-by":"publisher","unstructured":"Constum, T., et al.: Recognition and information extraction in historical handwritten tables: toward understanding early 20th century Paris census. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems, pp. 143\u2013157. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_10","DOI":"10.1007\/978-3-031-06555-2_10"},{"key":"23_CR6","doi-asserted-by":"publisher","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: DAN: a segmentation-free document attention network for handwritten document recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1\u201317 (2023). https:\/\/doi.org\/10.1109\/tpami.2023.3235826","DOI":"10.1109\/tpami.2023.3235826"},{"issue":"1","key":"23_CR7","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TPAMI.2022.3144899","volume":"45","author":"D Coquenet","year":"2023","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 508\u2013524 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3144899","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR8","unstructured":"Diaz, D.H., Qin, S., Ingle, R.R., Fujii, Y., Bissacco, A.: Rethinking text line recognition models. arXiv preprint arXiv:2104.07787 (2021)"},{"key":"23_CR9","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a048, pp. 1050\u20131059. PMLR, New York (2016). https:\/\/proceedings.mlr.press\/v48\/gal16.html"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Grosicki, E., El-Abed, H.: ICDAR 2011 - French Handwriting Recognition Competition. In: 2011 International Conference on Document Analysis and Recognition, pp. 1459\u20131463 (2011). https:\/\/doi.org\/10.1109\/ICDAR.2011.290","DOI":"10.1109\/ICDAR.2011.290"},{"key":"23_CR11","doi-asserted-by":"publisher","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML 2017), vol. 70, pp. 1321\u20131330 JMLR.org (2017). https:\/\/doi.org\/10.5555\/3305381.3305518","DOI":"10.5555\/3305381.3305518"},{"key":"23_CR12","unstructured":"Heafield, K.: KenLM: faster and smaller language model queries. In: Callison-Burch, C., Koehn, P., Monz, C., Zaidan, O.F. (eds.) Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 187\u2013197. Association for Computational Linguistics, Edinburgh (2011)"},{"key":"23_CR13","unstructured":"Kiessling, B.: The Kraken OCR System. https:\/\/kraken.re"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Kuang, Z., et al.: MMOCR: a comprehensive toolbox for text detection, recognition and understanding. arXiv preprint arXiv:2108.06543 (2021)","DOI":"10.1145\/3474085.3478328"},{"key":"23_CR15","doi-asserted-by":"publisher","unstructured":"Kumar, S., Nirschl, M., Holtmann-Rice, D., Liao, H., Suresh, A.T., Yu, F.: Lattice rescoring strategies for long short term memory language models in speech recognition. In: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 165\u2013172 (2017). https:\/\/doi.org\/10.1109\/ASRU.2017.8268931","DOI":"10.1109\/ASRU.2017.8268931"},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: Trocr: transformer-based optical character recognition with pre-trained models. In: AAAI Conference on Artificial Intelligence (2021). https:\/\/doi.org\/10.1609\/aaai.v37i11.26538","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: CASIA online and offline Chinese handwriting databases. In: 2011 International Conference on Document Analysis and Recognition, pp. 37\u201341 (2011). https:\/\/doi.org\/10.1109\/ICDAR.2011.17","DOI":"10.1109\/ICDAR.2011.17"},{"key":"23_CR18","doi-asserted-by":"publisher","unstructured":"Maarand, M., Beyer, Y., K\u00e5sen, A., Fosseide, K.T., Kermorvant, C.: A comprehensive comparison of open-source libraries for handwritten text recognition in Norwegian. In: Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, 22\u201325 May 2022, pp. 399\u2013413. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_27","DOI":"10.1007\/978-3-031-06555-2_27"},{"key":"23_CR19","first-page":"39","volume":"5","author":"UV Marti","year":"2002","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. 5, 39\u201346 (2002)","journal-title":"The IAM-database: an English sentence database for offline handwriting recognition."},{"key":"23_CR20","doi-asserted-by":"publisher","unstructured":"Muehlberger, G., Hackl, G.: NewsEye\/READ OCR training dataset from Austrian Newspapers (19th C.) (2019). https:\/\/doi.org\/10.5281\/zenodo.3387369","DOI":"10.5281\/zenodo.3387369"},{"key":"23_CR21","doi-asserted-by":"publisher","unstructured":"Neto, A.F.S., Bezerra, B.L.D., Toselli, A.H., Lima, E.B.: HTR-Flor++: a handwritten text recognition system based on a pipeline of optical and language models. In: Proceedings of the ACM Symposium on Document Engineering 2020 (DocEng 2020). Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3395027.3419603","DOI":"10.1145\/3395027.3419603"},{"key":"23_CR22","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (2011)"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a001, pp. 67\u201372 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.20","DOI":"10.1109\/ICDAR.2017.20"},{"key":"23_CR24","unstructured":"Puigcerver, J., Mochol\u00ed, C.: Pylaia. Commit SHA (2018). https:\/\/github.com\/jpuigcerver\/PyLaia\/"},{"key":"23_CR25","doi-asserted-by":"publisher","unstructured":"Romero, V., et al.: The ESPOSALLES database: an ancient marriage license corpus for off-line handwriting recognition. Pattern Recogn. 46(6), 1658\u20131669 (2013). https:\/\/doi.org\/10.1016\/j.patcog.2012.11.024","DOI":"10.1016\/j.patcog.2012.11.024"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM - an extensible language modeling toolkit. In: Interspeech (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"23_CR27","doi-asserted-by":"publisher","unstructured":"Stutzmann, D., Hamel, S., Kernier, I.D., M\u00fchlberger, G., Hackl, G.: HIMANIS Gu\u00e9rin, Type: dataset (2021). https:\/\/doi.org\/10.5281\/zenodo.5535306","DOI":"10.5281\/zenodo.5535306"},{"key":"23_CR28","doi-asserted-by":"publisher","unstructured":"Stutzmann, D., Torres\u00a0Aguilar, S., Chaffenet, P.: HOME-Alcar: aligned and annotated cartularies (2021). https:\/\/doi.org\/10.5281\/zenodo.5600884. Type: dataset","DOI":"10.5281\/zenodo.5600884"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Tarride, S., Boillet, M., Kermorvant, C.: Key-value information extraction from full handwritten pages. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition (ICDAR 2023), pp. 185\u2013204. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_11","DOI":"10.1007\/978-3-031-41679-8_11"},{"key":"23_CR30","doi-asserted-by":"publisher","unstructured":"Tarride, S., Faine, T., Boillet, M., Mouch\u00e8re, H., Kermorvant, C.: The belfort dataset: handwritten text recognition from crowdsourced annotations (2023). https:\/\/doi.org\/10.5281\/zenodo.8041668","DOI":"10.5281\/zenodo.8041668"},{"key":"23_CR31","doi-asserted-by":"publisher","unstructured":"Tassopoulou, V., Retsinas, G., Maragos, P.: Enhancing handwritten text recognition with N-gram sequence decomposition and multitask learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10555\u201310560. IEEE Computer Society, Los Alamitos (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412351","DOI":"10.1109\/ICPR48806.2021.9412351"},{"key":"23_CR32","doi-asserted-by":"publisher","unstructured":"Voigtlaender, P., Doetsch, P., Ney, H.: Handwriting recognition with large multidimensional long short-term memory recurrent neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 228\u2013233 (2016). https:\/\/doi.org\/10.1109\/ICFHR.2016.0052","DOI":"10.1109\/ICFHR.2016.0052"},{"key":"23_CR33","doi-asserted-by":"publisher","unstructured":"Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen, S.: Start, follow, read: end-to-end full-page handwriting recognition. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_23","DOI":"10.1007\/978-3-030-01231-1_23"},{"key":"23_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, H., Liang, L., Jin, L.: SCUT-HCCDoc: a new benchmark dataset of handwritten Chinese text in unconstrained camera-captured documents. Pattern Recognit. 107559 (2020). https:\/\/doi.org\/10.1016\/j.patcog.2020.107559","DOI":"10.1016\/j.patcog.2020.107559"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70549-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T09:09:28Z","timestamp":1725786568000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70549-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705489","9783031705496"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70549-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"9 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}